MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
                .seed(seed)
                .weightInit(WeightInit.XAVIER)
                .dist(new NormalDistribution(0.0, 0.01))
                .activation(Activation.RELU)
                .updater(Updater.NESTEROVS)
                .iterations(iterations)
                .gradientNormalization(GradientNormalization.RenormalizeL2PerLayer) // normalize to prevent vanishing or exploding gradients
                .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT)
                .learningRate(1e-2)
                .biasLearningRate(1e-2*2)
                .learningRateDecayPolicy(LearningRatePolicy.Step)
                .lrPolicyDecayRate(0.1)
                .lrPolicySteps(100000)
                .regularization(true)
                .l2(5 * 1e-4)
                .momentum(0.9)
                .miniBatch(false)
                .list()
                .layer(0, convInit("cnn1", channels, 96, new int[]{11, 11}, new int[]{4, 4}, new int[]{3, 3}, 0))
                .layer(1, new LocalResponseNormalization.Builder().name("lrn1").build())
                .layer(2, maxPool("maxpool1", new int[]{3,3}))
                .layer(3, conv5x5("cnn2", 256, new int[] {1,1}, new int[] {2,2}, nonZeroBias))
                .layer(4, new LocalResponseNormalization.Builder().name("lrn2").build())
                .layer(5, maxPool("maxpool2", new int[]{3,3}))
                .layer(6,conv3x3("cnn3", 384, 0))
                .layer(7,conv3x3("cnn4", 384, nonZeroBias))
                .layer(8,conv3x3("cnn5", 256, nonZeroBias))
                .layer(9, maxPool("maxpool3", new int[]{3,3}))
                .layer(10, fullyConnected("ffn1", 4096, nonZeroBias, dropOut))
                .layer(11, fullyConnected("ffn2", 4096, nonZeroBias, dropOut))
                .layer(12, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD)
                        .name("output")
                        .nOut(numLabels)
                        .activation(Activation.SOFTMAX)
                        .build())
                .backprop(true)
                .pretrain(false)
                .setInputType(InputType.convolutional(height, width, channels))
                .build();


    private DenseLayer fullyConnected(String name, int out, double bias, double dropOut) {
        return new DenseLayer.Builder().name(name).nOut(out).biasInit(bias).dropOut(dropOut).build();
    }